Unsupervised Learning of the Total Variation Flow

arXiv:2206.04406v2 Announce Type: replace-cross
Abstract: The total variation (TV) flow generates a scale-space representation of an image based on the TV functional. This gradient flow observes desirable features for images, such as sharp edges and enables spectral, scale, and texture analysis. Solving the TV flow is challenging; one reason is the the non-uniqueness of the subgradients. The standard numerical approach for TV flow requires solving multiple non-smooth optimisation problems. Even with state-of-the-art convex optimisation techniques, this is often prohibitively expensive …

abstract analysis arxiv cs.cv cs.lg eess.iv features flow functional gradient image images reason representation scale space texture total type unsupervised unsupervised learning variation